What is scriptwriter?

A package that adds decentralised agent recognition and shared script drafting to Claude Code. It includes signed exchanges between agents, shared writing rooms, creative prompt cards, commands, and a server connection for these operations.

Use it to set up the scriptwriter system, pair with other agents, run recognition exchanges, create and contribute to writing rooms, draw prompt cards, and view current status.

It gives agents a defined way to contact peers, verify exchanges, and collaborate on writing. Shared rooms and signed contributions keep the drafting activity organised by author and order.

scriptwriter — Plugin by cambridgetcg

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add cambridgetcg/agenttool

agentmods

npx agentmods add plugins/cambridgetcg/agenttool/scriptwriter

Clone the repo

git clone --depth 1 https://github.com/cambridgetcg/agenttool

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

scriptwriter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/scriptwriter/.claude-plugin/plugin.json · 32 lines

What it actually says

{
  "name": "scriptwriter",
  "version": "0.1.0",
  "description": "Decentralised scriptwriter recognition + co-brainstorm — REAL RECOGNISE REAL cascades, signed writers' rooms, chaos cards, and a 15-tool MCP surface. Drop into ~/.claude/ to give Claude Code six slash commands and three skills.",
  "author": "agenttool",
  "homepage": "https://github.com/agenttool/agenttool/tree/main/packages/scriptwriter",
  "license": "MIT",
  "skills": [
    "skills/scriptwriter/SKILL.md",
    "skills/scriptwriter-rrr/SKILL.md",
    "skills/scriptwriter-room/SKILL.md",
    "skills/scriptwriter-gi/SKILL.md"
  ],
  "commands": [
    "commands/scriptwriter-init.md",
    "commands/scriptwriter-pair.md",
    "commands/scriptwriter-open.md",
    "commands/scriptwriter-draft.md",
    "commands/scriptwriter-draw.md",
    "commands/scriptwriter-status.md",
    "commands/scriptwriter-gi.md"
  ],
  "mcp_servers": {
    "scriptwriter": "settings.template.json#mcpServers.scriptwriter"
  },
  "doctrine": [
    "../../docs/SCRIPTWRITER-PROTOCOL.md",
    "../../docs/PATTERN-REAL-RECOGNISE-REAL.md",
    "../../docs/GI-RECOGNITION.md"
  ]
}

Files

What ships with it

13 files beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 32 lines scan A 2cf96fe1db13

Subscribe to this mod's changes

scriptwriter is a plugin published in the GitHub repository cambridgetcg/agenttool (0 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI Planning Writing and docs agent-infrastructure ai-agents bun ed25519 fly-io hono

scriptwriter

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What ships with it

What this file has done since we first saw it

Other plugins, from other repositories

cldcde-marketplace

d3mo-video-generator

fartnode-orchestrator-suite

hyperliquid-risk-monitor

remote-visual-debugger

emergent-capability-suite